Influence of the vibro-acoustic sensor position on cavitation detection in a Kaplan turbine

Schmidt, Helmut; Kirschner, Oliver; Riedelbauch, Stefan; Necker, J; Kopf, E; Rieg, M; Arantes, G; Wessiak, M; Mayrhuber, J

doi:10.1088/1755-1315/22/5/052006

Cited by 10 publications

(19 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…While Principal Component Analysis (PCA) and feature selection are well-understood methods of developing health monitoring for systems, to our knowledge, this is the first work to apply this approach to hydroturbines. When compared to previous research aimed at comparing sensors, sensor placement, or CSPs, (Bajic, Services, Gmbh, & Zithe, 2003;Schmidt et al, 2014) our methodology uses a more objective, statistics-based approach to the evaluation process. It is important to note here that the method presented in this paper can discriminate between erosive and non-erosive cavitation which is important in the ultimate goal of determining RUL (not addressed in this paper).…”

Section: Specific Contributionsmentioning

confidence: 99%

See 1 more Smart Citation

Feature Selection for Monitoring Erosive Cavitation on a Hydroturbine

Gregg

Steele

Bossuyt³

2020

IJPHM

View full text Add to dashboard Cite

This paper presents a method for comparing and evaluating cavitation detection features - the first step towards estimating remaining useful life (RUL) of hydroturbine runners that areimpacted by erosive cavitation. The method can be used to quickly compare features created from cavitation survey data collected on any type of hydroturbine, sensor type, sensor location, and cavitation sensitivity parameter (CSP). Although manual evaluation and knowledge of hydroturbine cavitation is still required for our feature selection method, the use of principal component analysis greatly reduces the number of plots that require evaluation. We present a case study based on a cavitation survey data collected on a Francis hydroturbine located at a hydroelectric plant and demonstrate the selection of the most advantageous sensor type, sensor location, and CSP to use on this hydroturbine for long-term monitoring of erosive cavitation. Our method provides hydroturbine operators and researchers with a clear and effective means to determine preferred sensors, sensor placements, and CSPs while also laying the groundwork for determining RUL in the future.

show abstract

Section: Specific Contributionsmentioning

confidence: 99%

“…In experimental setups, sensors are sometimes attached to other locations including the hydroturbine case, test stand frame, or directly to the hydroturbine shaft. Sensor placement and orientation on one of the above identified locations can significantly impact the signal response as (Schmidt et al, 2014) shows.…”

Section: Sensor Type and Sensor Placementmentioning

confidence: 99%

Feature Selection for Monitoring Erosive Cavitation on a Hydroturbine

Gregg

Steele

Bossuyt³

2020

IJPHM

View full text Add to dashboard Cite

show abstract

“…Neill et al (1997) and Poddar and Tandon (2016) were able to detect cavitation incipience, their methods being based on the AE signals root mean squared (RMS) values that increase in amplitude and increasingly fluctuate when cavitation occurs. Analyzing parameters such as RMS and AE event energy and their fluctuation is a common approach, with typically good results (Boorsma and Fitzsimmons 2009;Boorsma and Whitworth 2011;Schmidt et al 2014Schmidt et al , 2015Look et al 2018). However, these calculated parameters lack the detection of individual cavitation impacts, as they tend to be temporally so close to each other that the parameter averaging interprets them as one.…”

Section: Introductionmentioning

confidence: 99%

Estimation of Cavitation Pit Distributions by Acoustic Emission

et al. 2020

View full text Add to dashboard Cite

Cavitation erosion in hydraulic machinery, such as in turbines and pumps, often leads to significant reduction of the service life of the affected components, with serious consequences for their maintenance costs and operation efficiency. In this study, the potential contribution of acoustic emission (AE) measurements to the assessment of cavitation damage is evaluated from experiments in a cavitation tunnel. Stainless steel samples were exposed to cavitation and damage was characterized from pitting tests carried out on mirror-polished samples. The pits were measured using an optical profilometer and cavitation damage was characterized by pit diameter distribution. In parallel, AE time signal was measured directly from behind the samples. A dedicated signal-processing technique was developed in order to identify each burst in the AE signal and determine its amplitude. The AE amplitude distribution compares well with PVDF and pressure sensor measurements from literature. It is concluded that AE signal analysis can be used to monitor the formation of pits without visual examination of the damaged surface. This provides a basis for possible future applications of nonintrusive cavitation erosion monitoring in hydraulic machines, provided the findings remain true in a more complex environment.

show abstract

“…Since visual detection of cavitation in a hydraulic power plant is not an option, acoustic event detection offers an alternative. Existing methods [1,2,3] rely on analyzing acoustics signals by designing statistical or handcrafted features, e.g. kurtosis.…”

Section: Introductionmentioning

confidence: 99%

Detection and Level Estimation of Cavitation in Hydraulic Turbines with Convolutional Neural Networks

Look¹,

Kirschner²,

Riedelbauch³

et al. 2018

Proceedings of the 10th International Symposium on Cavitation (CAV2018)

View full text Add to dashboard Cite

In this paper a method for detecting and furthermore estimating the intensity of cavitation occurrences in hydraulic turbines is presented. The method relies on analyzing high frequency signals with a convolutional neural network (CNN). The CNN is trained in an adversarial manner in order to get more robust results. After successful training the obtained network is modified in such a way, that it is possible to obtain estimations of the intensity. For evaluation purposes a separate dataset is investigated.

show abstract

Influence of the vibro-acoustic sensor position on cavitation detection in a Kaplan turbine

Cited by 10 publications

References 1 publication

Feature Selection for Monitoring Erosive Cavitation on a Hydroturbine

Feature Selection for Monitoring Erosive Cavitation on a Hydroturbine

Estimation of Cavitation Pit Distributions by Acoustic Emission

Detection and Level Estimation of Cavitation in Hydraulic Turbines with Convolutional Neural Networks

Contact Info

Product

Resources

About